© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 2129
    Prev
    Next
    INDEX
    Explanations

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    0.42
    openhagen
    0.41
     Möglichkeiten
    0.41
     मजबूत
    0.40
     পাঁচ
    0.39
    five
    0.38
     संवैधानिक
    0.38
    ۵
    0.38
     आसपास
    0.38
     उन
    0.38
    POSITIVE LOGITS
     your
    0.49
     jeweil
    0.44
    画面
    0.42
     calcula
    0.41
     the
    0.41
     betracht
    0.39
     fuit
    0.39
     prilikom
    0.38
     execution
    0.38
     output
    0.38
    Activations Density 1.566%

    No Known Activations